Intelligent Autonomous Ship Navigation using Multi-Sensor Modalities

Wright, R.G.

doi:10.12716/1001.13.03.03

Cited by 39 publications

(27 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It suggested building a standard based on autonomous cars; however, the main problem is that ships are larger and slower, but consequences of accidents may be more severe. The example research that focused on adaptive navigation of MASS in an uncertain environment was described in [7,13]. To achieve intelligent obstacle avoidance of MASS in coastal waters or a port, an autonomous navigation decision-making model based on dynamic programming method or hierarchical deep reinforcement machine learning was proposed.…”

Section: Related Workmentioning

confidence: 99%

“…To achieve intelligent obstacle avoidance of MASS in coastal waters or a port, an autonomous navigation decision-making model based on dynamic programming method or hierarchical deep reinforcement machine learning was proposed. Correspondingly, the use of machine learning and deep learning artificial intelligence (AI) techniques as a means to integrate multiple sensor modalities into a cohesive approach to navigation Sensors 2020, 20, 2075 3 of 25 for autonomous ships was presented in [13]. Finally, a System-Theoretic Process Analysis (STPA) was applied in the research presented in [11] in order to develop and analyse a preliminary model of the unmanned shipping system and elaborate safety recommendations for future developers of the actual system.…”

Section: Related Workmentioning

confidence: 99%

“…The algorithm of the GNSS positioning integrity assessment in maritime domain has been further developed by inclusion of a protection ellipse (PEmr), which is specified by 4 parameters, i.e.,: 1) semi-major axis of the estimated position error ellipse da [m], 2) semi-minor axis of the error ellipse db [m], 3) orientation of the error ellipse Φ, and 4) coverage factor k (see Figure 4). The parameters of formulae (12), (13), and (14) are derived from the square root of eigenvalues of the covariance matrix (9) confined to:…”

Section: Sbas-based Maritime Vessel Protection Area Conceptmentioning

confidence: 99%

See 2 more Smart Citations

Integrity Concept for Maritime Autonomous Surface Ships’ Position Sensors

Zalewski

2020

Sensors

View full text Add to dashboard Cite

The primary means for electronic position fixing currently in use in majority of contemporary merchant ships are shipborne GPS (Global Positioning System) receivers or DGPS (Differential GPS) and IALA (International Association of Lighthouse Authorities) radio beacon receivers. More advanced GNSS (Global Navigation Satellite System) receivers able to process signals from GPS, Russian GLONASS, Chinese Beidou, European Galileo, Indian IRNSS, Japan QZSS, and satellite-based augmentation systems (SBAS), are still relatively rare in maritime domain. However, it is expected that such combined or multi-system receivers will soon become more common in maritime transport and integrated with gyro, inertial, radar, laser, and optical sensors, and they will become indispensable onboard maritime autonomous surface ships (MASS). To be prepared for a malfunction of any position sensors, their state-of-the-art integrity monitoring should be developed and standardized, taking into account the specificity of MASS and e-navigation safety. The issues of existing requirements, performance standards, and future concepts of integrity monitoring for maritime position sensors are discussed and presented in this paper.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Sbas-based Maritime Vessel Protection Area Conceptmentioning

confidence: 99%

See 1 more Smart Citation

Integrity Concept for Maritime Autonomous Surface Ships’ Position Sensors

Zalewski

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The IPS is composed of various sensing equipment, sensing networks and information receiving equipment that collect the navigational information from the ship and the surrounding environment. In addition to safe and reliable hardware, the IPS also includes a suite of receiving software adapted to a variety of target information data formats [22], [23].…”

Section: A Compositionmentioning

confidence: 99%

A Methodology to Evaluate the Effectiveness of Intelligent Ship Navigational Information Monitoring System

Jun

Liu

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The perception and acquisition of navigation-related information are essential for the safety of intelligent ship. To address the effectiveness of navigational information monitoring system designed for the intelligent ship, in the present study, a comprehensive evaluation methodology is proposed. The various functions designed for obtaining corresponding navigational information are reorganized to develop the structure of intelligent ship navigational information monitoring system, which is subjected to evaluate the effectiveness by analyzing the information behavior processes in this proposed system and the available information monitoring technologies applied on intelligent ships. The orthogonal exploratory analysis technique was applied to establish the functional relationship between system effectiveness and contributing subsystems, as a result, the contribution degree distribution of contributing subsystems identified for system effectiveness is obtained. Finally, an application of the proposed methodology verifies its feasibility in calculating system effectiveness and its potential to extend to intelligent ships at different levels. The present study provides a new perspective to understand the safety of intelligent ships, and the comprehensive evaluation methodology provides a new path for the effectiveness analysis of intelligent ship navigational information monitoring system.

show abstract

“…ocean has been severely damaged because the large pollution gasses and high carbon emissions from fossil fuel combustion of large ships are excessively discharged into the ocean [1]. In the recent decade years, the whole world is facing a series of intractable problems brought by fossil energy such as environmental pollution, reduced reserves and non-renewable [3], [4], etc. Pure electric propulsion ships are the emerging green ships, which have the advantages of energy-saving, environmental protection and ''zero emission'', and have gradually become a key development direction of the most maritime powers [1].…”

Section: Introductionmentioning

confidence: 99%

A Data-Driven-Based Fault Diagnosis Approach for Electrical Power DC-DC Inverter by Using Modified Convolutional Neural Network With Global Average Pooling and 2-D Feature Image

et al. 2020

View full text Add to dashboard Cite

A novel convolutional neural network namely the modified CNN-GAP model is proposed for fast fault diagnosis of the DC-DC inverter. This method improves the model structure of the traditional CNN by using a global average pooling layer to replace the fully connected layer of 2∼3 layers. The improved CNN-GAP method mainly contains an input layer, a feature extraction layer, a global average pooling (GAP) layer, and a Softmax output layer. Firstly, the raw 1-D time-series data directly input into the input layer of the established CNN-GAP diagnosis model. The 2-D feature maps are reconstructed in the input layer. Secondly, the representative features are automatically extracted from the 2-D feature maps by using multiple convolutional layers and pooling layers. Thirdly, the dimension transformation and size compression of the output image of the feature extraction layer is completed by the GAP layer. Finally, the fault diagnosis result of the DC-DC inverter is automatically output in the Softmax output layer. The proposed method is used for diagnosing the open-circuit fault of the IGBT in the isolated DC-DC inverter. The proposed method is more accurate and effective than other mainstream intelligent diagnosis methods including the SVM, KNN, DNN, and traditional CNN. The experiment results show that the diagnostic accuracy is up to 99.95%, and the testing time can reduce by more than 15%. The improved CNN-GAP method could greatly reduce the model parameter quantity of the traditional CNN more than 80%, which is more suitable for rapid fault diagnosis in electronic devices. INDEX TERMS Intelligent fault diagnosis, data-driven, convolutional neural network, global average pooling, 2-D feature image, deep learning, DC-DC inverter, IGBT open-circuit fault.

show abstract

Intelligent Autonomous Ship Navigation using Multi-Sensor Modalities

Cited by 39 publications

References 2 publications

Integrity Concept for Maritime Autonomous Surface Ships’ Position Sensors

Integrity Concept for Maritime Autonomous Surface Ships’ Position Sensors

A Methodology to Evaluate the Effectiveness of Intelligent Ship Navigational Information Monitoring System

A Data-Driven-Based Fault Diagnosis Approach for Electrical Power DC-DC Inverter by Using Modified Convolutional Neural Network With Global Average Pooling and 2-D Feature Image

Contact Info

Product

Resources

About